22 March 1996 Comparison of function approximation with sigmoid and radial basis function networks
Author Affiliations +
Theoretical and computational results have demonstrated that several types of neural networks have the universal approximation property, i.e., the ability to represent any continuous function to an arbitrary degree of accuracy, given enough hidden units. However, practical considerations, such as the relative advantages of different networks for function approximation using a small to moderate number of hidden units, are not as well understood. This paper presents preliminary results of investigations into the comparison of networks using sigmoidal activation functions and networks using radial basis functions. In particular, we consider the ability of several such networks to learn mappings from the unit square to the real interval [0,1].
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Gary Russell, Gary Russell, Laurene V. Fausett, Laurene V. Fausett, } "Comparison of function approximation with sigmoid and radial basis function networks", Proc. SPIE 2760, Applications and Science of Artificial Neural Networks II, (22 March 1996); doi: 10.1117/12.235903; https://doi.org/10.1117/12.235903

Back to Top